This paper describes a new vision-based lane detection method for a driver assist system and an auto driving system. The vision-based lane detection often suffers from reduced visibility conditions. The method based on voting and multi resolution matching for the conditions is proposed. The performance of the proposed method has been investigated on 1,000 road images of reduced visibility conditions such as rainy and shadowy highway. 95 % detection rate is obtained in comparison with 81 % of the previous method. Thus the proposed method is effective for robustness of lane detection. (A*)
Abstract